Alert button
Picture for Taejin Park

Taejin Park

Alert button

TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context

Oct 08, 2021
Nithin Rao Koluguri, Taejin Park, Boris Ginsburg

Figure 1 for TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
Figure 2 for TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
Figure 3 for TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
Figure 4 for TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context
Viaarxiv icon

Robust Multi-channel Speech Recognition using Frequency Aligned Network

Feb 06, 2020
Taejin Park, Kenichi Kumatani, Minhua Wu, Shiva Sundaram

Figure 1 for Robust Multi-channel Speech Recognition using Frequency Aligned Network
Figure 2 for Robust Multi-channel Speech Recognition using Frequency Aligned Network
Figure 3 for Robust Multi-channel Speech Recognition using Frequency Aligned Network
Figure 4 for Robust Multi-channel Speech Recognition using Frequency Aligned Network
Viaarxiv icon